公开(公告)号：US11720559B2

公开(公告)日：2023-08-08

申请号：US17064466

申请日：2020-10-06

Applicant: salesforce.com, inc.

Inventor： Xi Lin ,  Caiming Xiong

IPC: G06F16/30 ,  G06F16/2452 ,  G06F16/21 ,  G06F16/22 ,  G06N3/088 ,  G06F16/242 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06F16/24522 ,  G06F16/212 ,  G06F16/2282 ,  G06F16/243 ,  G06N3/044 ,  G06N3/045 ,  G06N3/088

Abstract: A text-to-database neural network architecture is provided. The architecture receives a natural language question and a database schema and generates a serialized question-schema representation that includes a question and at least one table and at least one field from the database schema. The serialized question-schema representation is appended with at least one value that matches a word in the natural language question and at least one field in a database picklist. An encoder in the architecture generates question and schema encodings from the appended question-schema representation. Schema encodings are associated with metadata that indicates a data type of the fields and whether fields are associated with primary or foreign keys. A decoder in the architecture generates an executable query from the question encodings and schema encodings.

公开(公告)号：US20210173829A1

公开(公告)日：2021-06-10

申请号：US16866034

申请日：2020-05-04

Applicant: salesforce.com, inc.

Inventor： Jichuan Zeng ,  Xi Lin ,  Chu Hong Hoi

IPC: G06F16/242 ,  G06F40/284 ,  G06F40/47 ,  G06F16/2452

Abstract: A system and method for translating questions into database queries are provided. A text to database query system receives a natural language question and a structure in a database. Question tokens are generated from the question and query tokens are generated from the structure in the database. The question tokens and query tokens are concatenated into a sentence and a sentence token is added to the sentence. A BERT network generates question hidden states for the question tokens, query hidden states for the query tokens, and a classifier hidden state for the sentence token. A translatability predictor network determines if the question is translatable or untranslatable. A decoder converts a translatable question into an executable query. A confusion span predictor network identifies a confusion span in the untranslatable question that causes the question to be untranslatable. An auto-correction module to auto-correct the tokens in the confusion span.

公开(公告)号：US11727210B2

公开(公告)日：2023-08-15

申请号：US17162040

申请日：2021-01-29

Applicant: salesforce.com, inc.

Inventor： Qingyun Wang ,  Nazneen Rajani ,  Semih Yavuz ,  Xi Lin

IPC: G06F40/284 ,  G06F40/205 ,  G06F40/10

CPC classification number: G06F40/284 ,  G06F40/10 ,  G06F40/205

Abstract: Embodiments described herein provide systems and methods for data-to-text generation. The embodiments receive input data that includes a resource description framework (RDF) triples in an RDF graph. A data-to-text generation system generates position aware embeddings, including position embeddings, triple role embeddings, and tree-level embeddings. Using the position aware embeddings and the RDF graph, the data-to-text generation system generates a textual description for the RDF graph.

公开(公告)号：US11573957B2

公开(公告)日：2023-02-07

申请号：US16866034

申请日：2020-05-04

Applicant: salesforce.com, inc.

Inventor： Jichuan Zeng ,  Xi Lin ,  Chu Hong Hoi

IPC: G06F16/242 ,  G06F16/2452 ,  G06F40/47 ,  G06F40/284

Abstract: A system and method for translating questions into database queries are provided. A text to database query system receives a natural language question and a structure in a database. Question tokens are generated from the question and query tokens are generated from the structure in the database. The question tokens and query tokens are concatenated into a sentence and a sentence token is added to the sentence. A BERT network generates question hidden states for the question tokens, query hidden states for the query tokens, and a classifier hidden state for the sentence token. A translatability predictor network determines if the question is translatable or untranslatable. A decoder converts a translatable question into an executable query. A confusion span predictor network identifies a confusion span in the untranslatable question that causes the question to be untranslatable. An auto-correction module to auto-correct the tokens in the confusion span.

公开(公告)号：US20210374133A1

公开(公告)日：2021-12-02

申请号：US17064466

申请日：2020-10-06

Applicant: salesforce.com, inc.

Inventor： Xi Lin ,  Caiming Xiong

IPC: G06F16/2452 ,  G06F16/21 ,  G06F16/22 ,  G06F16/242 ,  G06N3/08 ,  G06N3/04

Abstract: A text-to-database neural network architecture is provided. The architecture receives a natural language question and a database schema and generates a serialized question-schema representation that includes a question and at least one table and at least one field from the database schema. The serialized question-schema representation is appended with at least one value that matches a word in the natural language question and at least one field in a database picklist. An encoder in the architecture generates question and schema encodings from the appended question-schema representation. Schema encodings are associated with metadata that indicates a data type of the fields and whether fields are associated with primary or foreign keys. A decoder in the architecture generates an executable query from the question encodings and schema encodings.